mlsanityData to 14 Oct 2026

CausalDialogue: Modeling Utterance-level Causality in Conversations

arXiv 2212.10515 ↗First posted 20 Dec 2022cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

Despite their widespread adoption, neural conversation models have yet to exhibit natural chat capabilities with humans. In this research, we examine user utterances as causes and generated responses as effects, recognizing that changes in a cause should produce a different effect. To further explore this concept, we have compiled and expanded upon a new dataset called CausalDialogue through crowd-sourcing. This dataset includes multiple cause-effect pairs within a directed acyclic graph (DAG) structure. Our analysis reveals that traditional loss functions struggle to effectively incorporate the DAG structure, leading us to propose a causality-enhanced method called Exponential Maximum Average Treatment Effect (ExMATE) to enhance the impact of causality at the utterance level in training neural conversation models. To evaluate the needs of considering causality in dialogue generation, we built a comprehensive benchmark on CausalDialogue dataset using different models, inference, and training methods. Through experiments, we find that a causality-inspired loss like ExMATE can improve the diversity and agility of conventional loss function and there is still room for improvement to reach human-level quality on this new dataset.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 33 of its 56 references that are in the map. First posted on arXiv 20 Dec 2022.

Builds on

33 of 56 references.

References · 33

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2022LaMDA: Language Models for Dialog Applicationscited by 1,220
  5. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,077
  6. 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
  7. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 828
  8. 2017DailyDialog: A Manually Labelled Multi-turn Dialogue Datasetcited by 652
  9. 2020Recipes for building an open-domain chatbotcited by 593
  10. 2019Neural Text Generation with Unlikelihood Trainingcited by 503
  11. 2016How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generationcited by 356
  12. 2016Deep Reinforcement Learning for Dialogue Generationcited by 288
21 more
  1. 2016A Persona-Based Neural Conversation Modelcited by 223
  2. 2017Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoderscited by 222
  3. 2015Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Modelscited by 207
  4. 2015A Neural Conversational Modelcited by 196
  5. 2015The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systemscited by 172
  6. 2017A Knowledge-Grounded Neural Conversation Modelcited by 136
  7. 2018Training Millions of Personalized Dialogue Agentscited by 126
  8. 2019Learning to Speak and Act in a Fantasy Text Adventure Gamecited by 122
  9. 2020MuTual: A Dataset for Multi-Turn Dialogue Reasoningcited by 115
  10. 2014word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding methodcited by 112
  11. 2017Adversarial Learning for Neural Dialogue Generationcited by 103
  12. 2015A Neural Network Approach to Context-Sensitive Generation of Conversational Responsescited by 98
  13. 2020Human-centric Dialog Training via Offline Reinforcement Learningcited by 93
  14. 2020Dialogue-Based Relation Extractioncited by 68
  15. 2016Dialogue Learning With Human-In-The-Loopcited by 46
  16. 2020How to Motivate Your Dragon: Teaching Goal-Driven Agents to Speak and Act in Fantasy Worldscited by 35
  17. 2022CHAI: A CHatbot AI for Task-Oriented Dialogue with Offline Reinforcement Learningcited by 34
  18. 2019DyKgChat: Benchmarking Dialogue Generation Grounding on Dynamic Knowledge Graphscited by 33
  19. 2018Game-Based Video-Context Dialoguecited by 15
  20. 2018Improving Conditional Sequence Generative Adversarial Networks by Stepwise Evaluationcited by 6
  21. 2021MultiTalk: A Highly-Branching Dialog Testbed for Diverse Conversationscited by 6

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024A Gradient Analysis Framework for Rewarding Good and Penalizing Bad Examples in Language Modelscited by 1